INDEX

Explanations

specific names or identifiers associated with individuals or characters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

atat

-0.15

lette

-0.15

agi

-0.15

iah

-0.14

ufen

-0.14

asted

-0.14

ToMany

-0.14

iltr

-0.14

lete

-0.14

ISA

-0.14

POSITIVE LOGITS

rove

0.16

ube

0.15

istique

0.15

@admin

0.15

_defaults

0.14

 sembl

0.14

fer

0.13

Ã³r

0.13

 alÄ±p

0.13

 slightest

0.13

Activations Density 0.002%

specific names or identifiers associated with individuals or characters

No Comments

No Known Activations