INDEX

Explanations

references to specific locations and attributes related to academic or legislative contexts

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

toi

-0.16

á»ĩ

-0.16

versions

-0.14

bay

-0.14

ichel

-0.14

iu

-0.14

.robot

-0.14

Rod

-0.13

/Grid

-0.13

ãĤ¸ãĤª

-0.13

POSITIVE LOGITS

elight

0.17

imas

0.16

PEND

0.15

elve

0.15

 Canc

0.14

 Halk

0.14

Lah

0.14

leen

0.13

Adds

0.13

anker

0.13

Activations Density 0.004%

references to specific locations and attributes related to academic or legislative contexts

No Comments

No Known Activations