INDEX

Explanations

references to vague or unspecified concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

sic

-0.16

(es

-0.15

ric

-0.15

ANGO

-0.15

pun

-0.14

.Native

-0.14

ritz

-0.14

axon

-0.14

lop

-0.14

ê¶ģ

-0.13

POSITIVE LOGITS

anol

0.15

/from

0.15

iner

0.14

adir

0.14

ÑĸÐ½ÑĮ

0.14

erras

0.14

Äįit

0.14

amentos

0.14

ril

0.14

Activations Density 0.096%

references to vague or unspecified concepts

No Comments

No Known Activations