INDEX

Explanations

negations or restrictive phrases related to availability and limitations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

æ¬ł

-0.18

ãĥªãĥ¼ãĤº

-0.16

akra

-0.15

rouch

-0.15

anes

-0.15

orno

-0.14

agger

-0.14

scar

-0.14

Axes

-0.14

exion

-0.14

POSITIVE LOGITS

sm

0.15

GetInstance

0.14

ëł

0.14

iddi

0.14

 midnight

0.14

early

0.13

eken

0.13

 Surprise

0.13

 Britt

0.13

elligent

0.13

Activations Density 0.485%

negations or restrictive phrases related to availability and limitations

No Comments

No Known Activations