INDEX

Explanations

conditional statements and phrases related to choices or possibilities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

aque

-0.17

atto

-0.16

lagen

-0.15

krom

-0.14

Criterion

-0.14

peg

-0.13

tron

-0.13

adel

-0.13

itious

-0.13

Î¿Ïģ

-0.13

POSITIVE LOGITS

OCUS

0.15

RIPT

0.14

mez

0.14

ika

0.14

 sentiment

0.14

ÏĢÏīÏĤ

0.14

lica

0.13

meden

0.13

tes

0.13

ica

0.13

Activations Density 0.029%

conditional statements and phrases related to choices or possibilities

No Comments

No Known Activations