INDEX

Explanations

references to individuals who previously held notable positions or roles

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

kon

-0.15

Ret

-0.15

-0.14

 broad

-0.14

 Bowie

-0.14

yc

-0.14

POSITIVE LOGITS

avad

0.16

ediator

0.16

riad

0.15

ARRIER

0.15

ompiler

0.15

utex

0.15

Ngh

0.14

_TAC

0.14

ì±ħ

0.14

eyh

0.14

Activations Density 0.008%

references to individuals who previously held notable positions or roles

No Comments

No Known Activations