INDEX

Explanations

references to specific subjects and pronouns in the text

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

ocks

-0.18

swire

-0.17

ance

-0.15

rang

-0.15

ed

-0.14

vals

-0.14

 Diaz

-0.14

Nej

-0.14

orst

-0.14

ÑģÑĤÐ¸Ð½

-0.14

POSITIVE LOGITS

'&&

0.15

ritch

0.15

Â¤Â¤

0.15

Ã©ry

0.14

flater

0.13

 absent

0.13

isse

0.13

_TA

0.13

pond

0.13

 Boeh

0.13

Activations Density 0.144%

references to specific subjects and pronouns in the text

No Comments

No Known Activations