INDEX

Explanations

instances of text that suggest an action to save or return to content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

olar

-0.15

VEC

-0.15

acci

-0.15

Ã¼lÃ¼k

-0.15

 éĥ

-0.14

zero

-0.14

monic

-0.14

olars

-0.14

anza

-0.14

nnen

-0.14

POSITIVE LOGITS

æĢª

0.18

elo

0.15

(fn

0.14

wy

0.14

(compact

0.14

ury

0.14

etter

0.14

eland

0.14

roud

0.14

earch

0.14

Activations Density 0.023%

instances of text that suggest an action to save or return to content

No Comments

No Known Activations