INDEX

Explanations

references to academic programs and initiatives

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

-0.15

Wan

-0.14

åħ¨åĽ½

-0.14

Subviews

-0.14

æŁ

-0.13

ados

-0.13

avern

-0.13

Ø¨ÙĬØ±

-0.13

xab

-0.13

_jet

-0.13

POSITIVE LOGITS

rax

0.19

idis

0.17

/umd

0.17

ept

0.16

Î¼Î¼

0.15

rvine

0.15

ARS

0.14

yt

0.14

ars

0.14

(HttpContext

0.14

Activations Density 0.504%

references to academic programs and initiatives

No Comments

No Known Activations