INDEX

Explanations

names and specific terms related to individuals or characters

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

ãĥ¼ãĥ

-0.14

StackNavigator

-0.14

/fire

-0.14

uko

-0.14

rend

-0.14

ulla

-0.14

estatus

-0.14

*)_

-0.13

_LAYER

-0.13

uur

-0.13

POSITIVE LOGITS

jit

0.17

acc

0.16

swe

0.16

oyo

0.16

sworth

0.15

oto

0.15

sey

0.15

ison

0.14

rror

0.14

Activations Density 0.093%

names and specific terms related to individuals or characters

No Comments

No Known Activations