INDEX

Explanations

events and specific dates in historical contexts

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

-0.19

ffa

-0.14

 recent

-0.14

_angles

-0.13

èª

-0.13

ëıĦë¡ľ

-0.13

¯

-0.13

 ãĤ¢ãĤ¤

-0.13

owie

-0.13

aÅ¼

-0.13

POSITIVE LOGITS

aret

0.19

ween

0.16

ilk

0.15

iling

0.14

 ghost

0.14

Rao

0.14

 Sanat

0.14

isphere

0.13

çĿĢ

0.13

]={↵

0.13

Activations Density 0.080%

events and specific dates in historical contexts

No Comments

No Known Activations