INDEX

Explanations

references to small or fragmented pieces of information or data

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

pj

-0.16

///<

-0.15

ettes

-0.15

-0.14

ãĥ³ãĥĩ

-0.14

ispers

-0.14

efon

-0.14

cmp

-0.14

ationToken

-0.14

-0.13

POSITIVE LOGITS

ëŀĢ

0.15

_algo

0.15

odi

0.15

.AutoComplete

0.15

ziel

0.14

é©

0.14

zk

0.14

Ø¦

0.14

usz

0.14

orado

0.14

Activations Density 0.007%

references to small or fragmented pieces of information or data

No Comments

No Known Activations