INDEX

Explanations

references to directions and navigation instructions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

byn

-0.16

otch

-0.15

ÑĢÑĥÐºÑĤ

-0.15

 ì¸

-0.14

/Grid

-0.14

meni

-0.14

Voj

-0.14

ISO

-0.14

é¢

-0.14

ancia

-0.13

POSITIVE LOGITS

ropic

0.15

abal

0.15

resses

0.15

ograf

0.15

ologies

0.14

 trainable

0.14

wick

0.14

 coping

0.14

imir

0.14

Activations Density 0.243%

references to directions and navigation instructions

No Comments

No Known Activations

references to directions and navigation instructions

No Comments

No Known Activations