INDEX

Explanations

names of individuals mentioned 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 @ 8-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

rone

-0.17

ingly

-0.16

ingen

-0.15

shade

-0.14

ÂŃing

-0.14

spath

-0.14

sson

-0.14

opies

-0.14

inge

-0.13

POSITIVE LOGITS

 TMPro

0.16

 distress

0.15

.scalablytyped

0.14

 Sources

0.14

 lesbi

0.14

aser

0.13

 Wald

0.13

intros

0.13

Sources

0.13

/***/

0.13

Activations Density 0.044%

names of individuals mentioned in the text

No Comments

No Known Activations