INDEX

Explanations

specific names and titles related to authority figures and prominent individuals

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

.generated

-0.18

readcr

-0.17

 Ð¿ÑĢÐ°Ð²Ð´Ð°

-0.15

.Prot

-0.14

ienda

-0.14

bitmap

-0.13

ollen

-0.13

ossa

-0.13

hy

-0.13

WSC

-0.13

POSITIVE LOGITS

 Barrel

0.19

bourne

0.15

ottle

0.15

avit

0.15

Ã¡d

0.15

ìĪĻ

0.14

ÏĢÎ¿ÏĦÎµ

0.14

idos

0.14

 ÐŀÑģÐ¾Ð±

0.14

angan

0.13

Activations Density 0.001%

specific names and titles related to authority figures and prominent individuals

No Comments

No Known Activations