INDEX

Explanations

instances where something is being defined or detailed

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

ution

-0.19

swick

-0.16

icom

-0.15

Ged

-0.15

 Cliff

-0.15

inson

-0.15

á»±

-0.14

si

-0.14

inki

-0.14

 surprises

-0.14

POSITIVE LOGITS

.scalablytyped

0.18

AGES

0.15

 æļ

0.15

èĻİ

0.15

://"

0.14

ãĥ¼ãĥĦ

0.14

rou

0.14

ÑıÐ´

0.14

Activations Density 0.014%

instances where something is being defined or detailed

No Comments

No Known Activations