INDEX

Explanations

terms related to membership or possession

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

llib

-0.16

lle

-0.15

ffe

-0.15

uell

-0.15

resse

-0.15

Ø§ÙģØª

-0.15

riel

-0.15

rana

-0.14

Ã¤ll

-0.14

utr

-0.14

POSITIVE LOGITS

(ed

0.20

gers

0.20

 nowhere

0.20

ents

0.19

ÂŃing

0.17

ading

0.17

ent

0.16

Sizer

0.16

 belong

0.16

 together

0.16

Activations Density 0.012%

terms related to membership or possession

No Comments

No Known Activations