INDEX

Explanations

punctuation marks, specifically ellipses and dashes indicating pauses or omitted text

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

rescia

-0.15

iale

-0.14

rg

-0.14

ÑĢÐ¾Ð²Ð°Ð½

-0.14

okrat

-0.14

 Baxter

-0.14

okt

-0.13

gorith

-0.13

manuel

-0.13

 Rich

-0.13

POSITIVE LOGITS

insky

0.18

FML

0.15

Ð¾Ð²Ð¸Ñĩ

0.15

sian

0.15

edList

0.15

vÄĽd

0.14

toMatch

0.14

TERM

0.14

 rais

0.14

osi

0.14

Activations Density 0.018%

punctuation marks, specifically ellipses and dashes indicating pauses or omitted text

No Comments

No Known Activations