INDEX

Explanations

repeated mentions of a specific name or term related to an individual's achievements and career

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

åĴ

-0.15

.lucene

-0.15

eny

-0.14

esi

-0.13

 backwards

-0.13

ersiz

-0.13

åĨł

-0.13

 Helm

-0.13

inks

-0.13

inery

-0.13

POSITIVE LOGITS

ottie

0.16

tec

0.15

mana

0.15

onces

0.15

rias

0.14

lox

0.14

kins

0.14

TO

0.14

.SetParent

0.14

shaft

0.14

Activations Density 0.023%

repeated mentions of a specific name or term related to an individual's achievements and career

No Comments

No Known Activations