INDEX

Explanations

prepositions indicating focus or direction

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

bh

-0.16

PT

-0.15

ãĤīãģı

-0.15

åł

-0.15

åĻ

-0.15

HEMA

-0.15

anzi

-0.14

ÙĪÛĮØ²ÛĮ

-0.14

_OCCURRED

-0.14

ãĥ¼ãĥ©

-0.14

POSITIVE LOGITS

 Bene

0.14

phys

0.14

/fixtures

0.14

 focus

0.14

 circum

0.14

the

0.14

iza

0.14

lix

0.14

.tex

0.14

focus

0.14

Activations Density 0.025%

prepositions indicating focus or direction

No Comments

No Known Activations