INDEX

Explanations

references to governmental or organizational authority

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

LEM

-0.16

wner

-0.15

.cljs

-0.15

positor

-0.14

áº«

-0.14

ufe

-0.13

ãĥĳãĥ³

-0.13

klÃ¤

-0.13

voie

-0.13

Łèĥ½

-0.13

POSITIVE LOGITS

eldon

0.15

rieve

0.15

thest

0.14

usto

0.13

 Ð´Ð²Ð¾

0.13

fur

0.13

 hobbies

0.13

pra

0.13

Activations Density 0.109%

references to governmental or organizational authority

No Comments

No Known Activations