INDEX

Explanations

names or terms related to entries or mentions, particularly focusing on multiple instances of the suffix "rey" and "ent."

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

ilton

-0.15

axe

-0.15

 aggreg

-0.15

stay

-0.14

vell

-0.14

_dtype

-0.14

 Cone

-0.14

æĸĻ

-0.14

 recess

-0.14

-0.13

POSITIVE LOGITS

osate

0.19

avourites

0.17

pNet

0.16

blogs

0.16

elles

0.15

SWG

0.15

endance

0.15

 Rodgers

0.14

RID

0.14

perature

0.14

Activations Density 0.007%

names or terms related to entries or mentions, particularly focusing on multiple instances of the suffix "rey" and "ent."

No Comments

No Known Activations