INDEX

Explanations

references to membership or affiliation with groups and organizations

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

ulp

-0.15

omm

-0.15

 portions

-0.15

enders

-0.15

pter

-0.15

angkan

-0.14

ERSHEY

-0.14

ands

-0.14

oine

-0.14

enth

-0.14

POSITIVE LOGITS

acus

0.15

 anonymous

0.15

Unchecked

0.14

von

0.14

_avail

0.14

 part

0.14

annels

0.13

von

0.13

erm

0.13

Activations Density 0.082%

references to membership or affiliation with groups and organizations

No Comments

No Known Activations