INDEX

Explanations

punctuation marks and structural elements within numerical data or lists

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

uft

-0.15

|required

-0.15

iken

-0.15

aret

-0.15

ogen

-0.14

bourg

-0.14

_Response

-0.14

ault

-0.14

arn

-0.14

ilet

-0.13

POSITIVE LOGITS

 McGr

0.16

richt

0.15

achu

0.15

åīĽ

0.14

nic

0.14

essler

0.14

chw

0.14

Lay

0.14

AYS

0.14

alue

0.13

Activations Density 0.004%

punctuation marks and structural elements within numerical data or lists

No Comments

No Known Activations