INDEX

Explanations

instances of notable identifiers or categories related to people, events, or classifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

ntag

-0.18

annies

-0.16

AZY

-0.16

ogh

-0.16

éĺħè¯»æ¬¡æķ°

-0.15

nock

-0.14

<message

-0.14

thur

-0.14

Ð½Ð°Ð´Ð»ÐµÐ¶

-0.14

actus

-0.14

POSITIVE LOGITS

tet

0.15

ÑĪÐ¸Ð²

0.14

 Fallen

0.14

lier

0.14

esse

0.14

ÑģÑĤÐ¸

0.14

isch

0.14

connection

0.14

Tet

0.14

 harms

0.14

Activations Density 0.019%

instances of notable identifiers or categories related to people, events, or classifications

No Comments

No Known Activations