INDEX

Explanations

instances of reported speech or quotation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

.fm

-0.16

eur

-0.15

uisse

-0.15

ovu

-0.15

ToolStripMenuItem

-0.14

ukan

-0.14

orraine

-0.14

etary

-0.14

velle

-0.13

amon

-0.13

POSITIVE LOGITS

0.17

igham

0.15

 there

0.15

aran

0.15

it

0.14

itler

0.14

esen

0.14

onia

0.13

 subt

0.13

Activations Density 0.037%

instances of reported speech or quotation

No Comments

No Known Activations