INDEX

Explanations

phrases that express positive sentiments or evaluations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

($)

-0.15

 this

-0.15

 denominator

-0.15

WA

-0.15

opause

-0.14

 entering

-0.14

id

-0.14

 proven

-0.14

 these

-0.14

POSITIVE LOGITS

_CHILD

0.16

,buf

0.15

spb

0.15

 bÃ¬

0.15

abyrin

0.15

kir

0.14

 Ø§ÙĦØ±ÙħØ²ÙĬØ©

0.14

dra

0.14

undle

0.14

CLU

0.14

Activations Density 0.101%

phrases that express positive sentiments or evaluations

No Comments

No Known Activations