INDEX

Explanations

specific vocal sounds or phonetic representations in text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

_simps

-0.16

lt

-0.15

dana

-0.15

ANDOM

-0.15

mary

-0.15

ienne

-0.15

iant

-0.14

geme

-0.14

firm

-0.14

za

-0.14

POSITIVE LOGITS

raft

0.17

Ð²Ð¾ÑĢ

0.17

allback

0.15

etre

0.15

 Aires

0.15

Ð°Ð¹Ð´

0.15

æģµ

0.15

appings

0.15

athers

0.14

Ear

0.14

Activations Density 0.167%

specific vocal sounds or phonetic representations in text

No Comments

No Known Activations