INDEX

Explanations

mentions of "first" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

endo

-0.17

TRACE

-0.16

htdocs

-0.15

abee

-0.15

Ä±rak

-0.15

llib

-0.15

ableView

-0.14

éĨ´

-0.14

igest

-0.14

 herr

-0.14

POSITIVE LOGITS

-ever

0.19

 Nimbus

0.15

KV

0.15

 ever

0.15

/original

0.14

ham

0.14

 Coord

0.14

tom

0.14

 anale

0.14

/basic

0.13

Activations Density 0.049%

mentions of "first" in various contexts

No Comments

No Known Activations