INDEX

Explanations

references to locations or geographic directions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

illes

-0.18

 Schmidt

-0.15

 Sloan

-0.15

ãĤĤãģ®

-0.14

ë¨

-0.14

sass

-0.14

UIL

-0.13

ulle

-0.13

egov

-0.13

_mono

-0.13

POSITIVE LOGITS

 MATRIX

0.17

 Grace

0.15

di

0.14

alars

0.14

reeNode

0.14

atonin

0.14

 comp

0.14

»

0.14

 Randall

0.14

Activations Density 0.007%

references to locations or geographic directions

No Comments

No Known Activations