INDEX

Explanations

phrases related to conflicts of interest in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

adar

-0.17

zimmer

-0.16

vette

-0.15

ivre

-0.15

lettes

-0.15

_WM

-0.15

lsa

-0.14

ELY

-0.14

ktion

-0.14

APPER

-0.14

POSITIVE LOGITS

0.17

killer

0.15

agon

0.15

atas

0.15

MC

0.14

MEM

0.14

 astr

0.14

Activations Density 0.084%

phrases related to conflicts of interest in various contexts

No Comments

No Known Activations