INDEX

Explanations

references to the term "Virgin" and its variations in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

umba

-0.19

ãĥ¼ãĤ

-0.16

raman

-0.16

argo

-0.16

arg

-0.16

raig

-0.15

ARGS

-0.15

gie

-0.15

zzo

-0.15

REFIX

-0.14

POSITIVE LOGITS

iami

0.17

aires

0.17

ity

0.17

ourse

0.16

nez

0.15

ÐłÐĿ

0.15

Ã¼s

0.15

head

0.14

Ľ°

0.14

.subscribe

0.14

Activations Density 0.034%

references to the term "Virgin" and its variations in various contexts

No Comments

No Known Activations