INDEX

Explanations

expressions of opinion or subjective evaluations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

uth

-0.19

lev

-0.16

wan

-0.14

anova

-0.14

den

-0.14

ought

-0.13

UTH

-0.13

StackNavigator

-0.13

 Princip

-0.13

.af

-0.13

POSITIVE LOGITS

MBED

0.15

ampo

0.15

ìłķ

0.14

lisi

0.14

éģĩ

0.14

à¸¸à¸Ľ

0.14

pherical

0.14

([$

0.14

ysz

0.14

TTY

0.14

Activations Density 0.090%

expressions of opinion or subjective evaluations

No Comments

No Known Activations