INDEX

Explanations

names and references to specific individuals

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

emes

-0.15

aho

-0.14

 Garn

-0.14

ÑĢÑĥÐ¶

-0.14

 Pear

-0.14

etik

-0.13

-sc

-0.13

 Carly

-0.13

{*

-0.13

nbsp

-0.13

POSITIVE LOGITS

YY

0.15

steen

0.15

oes

0.14

maj

0.14

hsi

0.14

COLUMN

0.14

enden

0.14

udiant

0.13

Ã¶ren

0.13

ovice

0.13

Activations Density 0.067%

names and references to specific individuals

No Comments

No Known Activations