INDEX

Explanations

phrases related to revisiting or checking back for updates

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

oidal

-0.15

assy

-0.15

opia

-0.14

ÏģÏį

-0.14

aho

-0.14

.PropTypes

-0.14

_SIMPLE

-0.14

ombres

-0.13

raci

-0.13

ent

-0.13

POSITIVE LOGITS

isd

0.17

FTA

0.15

PLICIT

0.15

imde

0.14

ERAL

0.14

 Gian

0.14

>window

0.14

 sens

0.14

IPA

0.14

datable

0.14

Activations Density 0.015%

phrases related to revisiting or checking back for updates

No Comments

No Known Activations