INDEX

Explanations

phrases reflecting statements or assertions

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

steder

-0.17

ãĥ³ãĥĩ

-0.16

çı

-0.15

ç²Ĵ

-0.14

_FOREACH

-0.14

Uvs

-0.14

ØªÙĦ

-0.13

ãĥ¯ãĥ¼

-0.13

Ð°ÑĢÐ°Ð½

-0.13

mia

-0.13

POSITIVE LOGITS

ibir

0.15

iliz

0.14

ehr

0.14

onto

0.14

rames

0.14

 Angiospermae

0.14

 Hodg

0.14

ACK

0.14

HT

0.13

rippling

0.13

Activations Density 0.189%

phrases reflecting statements or assertions

No Comments

No Known Activations