INDEX

Explanations

expressions indicating something is regarded as notable or of significance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

azor

-0.17

olin

-0.17

gle

-0.15

osta

-0.14

claimer

-0.14

okin

-0.13

opy

-0.13

elin

-0.13

ingo

-0.13

doch

-0.13

POSITIVE LOGITS

 somewhat

0.18

hof

0.16

 having

0.16

sac

0.16

 sacred

0.15

ately

0.15

aghan

0.15

 part

0.15

 synonymous

0.15

Activations Density 0.072%

expressions indicating something is regarded as notable or of significance

No Comments

No Known Activations