INDEX

Explanations

references to specific authors and their works

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

resi

-0.16

atti

-0.16

Nib

-0.15

DebugEnabled

-0.15

ibold

-0.15

hod

-0.15

lobs

-0.15

STA

-0.14

icast

-0.14

Ī¬

-0.14

POSITIVE LOGITS

imately

0.15

 ÑģÐ¾Ð²

0.14

 proport

0.14

.scalablytyped

0.14

Eh

0.14

chnitt

0.14

 setC

0.14

unset

0.14

ort

0.14

svc

0.13

Activations Density 0.150%

references to specific authors and their works

No Comments

No Known Activations