INDEX

Explanations

conjunctions and references to adding or emphasizing qualities within descriptions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

oog

-0.17

 Keys

-0.17

ugas

-0.16

 keys

-0.14

Soap

-0.14

 spoilers

-0.14

aptive

-0.14

Ð¼

-0.13

ocular

-0.13

turnstile

-0.13

POSITIVE LOGITS

ead

0.15

SizePolicy

0.15

ilton

0.15

 Papa

0.14

ione

0.14

eg

0.14

èŃ

0.13

 straightforward

0.13

WT

0.13

eb

0.13

Activations Density 0.026%

conjunctions and references to adding or emphasizing qualities within descriptions

No Comments

No Known Activations