INDEX

Explanations

structured data references, particularly related to programming and data manipulation

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

RuleContext

-0.17

↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵

-0.16

ogn

-0.15

eways

-0.15

bone

-0.15

akening

-0.14

etCode

-0.14

ãĥį

-0.14

orrow

-0.14

venue

-0.14

POSITIVE LOGITS

 )↵↵↵↵↵↵↵↵

0.16

âĻ¥

0.15

 -------------------------------------------------------------------------

0.15

;↵↵↵

0.14

Ø§Ø°

0.14

 :↵↵↵↵

0.14

 opposing

0.14

ATOR

0.14

({↵↵

0.14

 AssemblyVersion

0.14

Activations Density 0.168%

structured data references, particularly related to programming and data manipulation

No Comments

No Known Activations