INDEX

Explanations

numerical references or counts within a context

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

IOC

-0.14

iciency

-0.14

iola

-0.14

iag

-0.14

olic

-0.14

luv

-0.14

ÃŃl

-0.13

oine

-0.13

 tras

-0.13

irie

-0.13

POSITIVE LOGITS

æ´

0.14

ndx

0.14

remen

0.14

 fitte

0.14

ZIP

0.13

bine

0.13

odel

0.13

_SIGNATURE

0.13

&W

0.13

Activations Density 0.001%

numerical references or counts within a context

No Comments

No Known Activations