INDEX

Explanations

terms related to various types of cancer and medical conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

eller

-0.15

Ð½Ð¸Ð½

-0.15

jur

-0.15

Ain

-0.15

iggins

-0.15

oling

-0.14

dna

-0.14

.vs

-0.14

 Morrison

-0.14

ylland

-0.14

POSITIVE LOGITS

_apps

0.16

0.15

0.14

utz

0.14

Poz

0.14

ĵĺ

0.14

izr

0.13

 ÎłÎ±

0.13

(s

0.13

PW

0.13

Activations Density 0.389%

terms related to various types of cancer and medical conditions

No Comments

No Known Activations