INDEX

Explanations

instances of the word "Posted" followed by a number, indicating the posting of content

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

 habit

-0.16

éľ

-0.15

 swath

-0.15

ra

-0.14

asta

-0.14

ran

-0.14

fet

-0.14

azzo

-0.14

arily

-0.14

ners

-0.14

POSITIVE LOGITS

esel

0.15

ophy

0.15

 Ø§ÙĦÙħØ¤

0.15

enek

0.15

gend

0.14

OrNil

0.14

ivec

0.14

dik

0.14

esome

0.14

 èĩªåĬ¨çĶŁæĪĲ

0.14

Activations Density 0.004%

instances of the word "Posted" followed by a number, indicating the posting of content

No Comments

No Known Activations