INDEX

Explanations

references to external influences or outside factors

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

allee

-0.15

ìŀĲê¸°

-0.15

 jadx

-0.15

Ð¾Ð¿Ð°Ñģ

-0.15

gue

-0.14

ãĤ¹ãĤ¯

-0.14

pane

-0.14

ingular

-0.14

áº¯p

-0.14

iaux

-0.14

POSITIVE LOGITS

Outside

0.16

 outside

0.16

 Outside

0.16

 external

0.16

/internal

0.15

outside

0.15

halb

0.15

ication

0.15

bery

0.15

Activations Density 0.027%

references to external influences or outside factors

No Comments

No Known Activations