INDEX

Explanations

references to historical events or concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

ience

-0.16

-fontawesome

-0.14

 undef

-0.14

erator

-0.14

ipo

-0.14

ÙĬØ§Øª

-0.14

itude

-0.14

vat

-0.14

hem

-0.14

(CH

-0.13

POSITIVE LOGITS

 Hlav

0.15

GD

0.15

 Goldberg

0.15

 guilt

0.14

dera

0.14

ĥĿ

0.14

ãĥ

0.14

Ø³ÙĪ

0.13

 ÑģÑĥÐ¼

0.13

emann

0.13

Activations Density 0.002%

references to historical events or concepts

No Comments

No Known Activations