INDEX

Explanations

phrases indicating a sequence or plan for future actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

rus

-0.17

 Gall

-0.17

lesc

-0.15

zin

-0.15

hausen

-0.15

ä¾į

-0.14

phia

-0.14

loses

-0.14

sher

-0.14

ORIZ

-0.14

POSITIVE LOGITS

 forc

0.15

olan

0.15

anh

0.15

deme

0.14

xo

0.14

ari

0.14

onden

0.14

ektiv

0.14

aphore

0.13

ÄĽk

0.13

Activations Density 0.007%

phrases indicating a sequence or plan for future actions

No Comments

No Known Activations