INDEX

Explanations

references to films and their associated attributes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

itz

-0.16

lick

-0.16

aler

-0.14

 akci

-0.14

otton

-0.14

ollo

-0.13

ÄĽr

-0.13

 seizure

-0.13

axon

-0.13

POSITIVE LOGITS

ä½ľ

0.18

eree

0.16

.sap

0.16

_cleanup

0.15

::*

0.15

riday

0.14

acd

0.14

scribe

0.14

cribe

0.14

 Past

0.14

Activations Density 0.062%

references to films and their associated attributes

No Comments

No Known Activations