INDEX

Explanations

conditional statements involving personal choices and preferences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

ufen

-0.16

leyin

-0.15

-safe

-0.14

å¾ħ

-0.14

ãĥ¥ãĥ¼

-0.14

safe

-0.13

Survey

-0.13

yun

-0.13

MLS

-0.13

POSITIVE LOGITS

µ

0.17

 yoksa

0.17

ensitive

0.16

 sensitive

0.15

ALAR

0.15

oj

0.15

reature

0.14

Ð½Ð¸Ð¼Ð°

0.14

plans

0.14

é«ĺåº¦

0.14

Activations Density 0.170%

conditional statements involving personal choices and preferences

No Comments

No Known Activations

conditional statements involving personal choices and preferences

No Comments

No Known Activations