INDEX

Explanations

references to specific years or dates

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

lix

-0.15

èªł

-0.15

ulong

-0.14

Ø°Ø§

-0.14

 Loose

-0.14

ventus

-0.14

AYOUT

-0.13

BaseUrl

-0.13

Ð½Ð¾Ð¶

-0.13

fund

-0.13

POSITIVE LOGITS

 against

0.17

anger

0.16

 councils

0.15

against

0.15

 Against

0.14

oad

0.14

itational

0.14

Against

0.14

ason

0.14

egis

0.14

Activations Density 0.012%

references to specific years or dates

No Comments

No Known Activations