INDEX

Explanations

references to tall structures or heights

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

GLOSS

-0.15

ÑĽ

-0.14

 Gott

-0.14

ÐµÐ¿ÑĤÐ¸

-0.14

uality

-0.14

ienia

-0.14

asis

-0.14

vala

-0.13

ÐµÑĢÐ¾

-0.13

ialect

-0.13

POSITIVE LOGITS

itur

0.17

ga

0.16

ajo

0.16

.Magenta

0.16

 Pawn

0.16

otel

0.15

apiro

0.15

ickers

0.15

enna

0.14

antages

0.14

Activations Density 0.054%

references to tall structures or heights

No Comments

No Known Activations