INDEX

Explanations

percentage and ratio details within texts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

asel

-0.16

lÃ¢m

-0.15

THEN

-0.15

orum

-0.14

LLU

-0.14

	then

-0.14

oster

-0.14

sey

-0.14

ivre

-0.14

vit

-0.14

POSITIVE LOGITS

Erg

0.16

hole

0.15

æĬĺ

0.14

hol

0.14

Hol

0.14

ying

0.14

_exact

0.14

0.13

 Prot

0.13

Activations Density 0.308%

percentage and ratio details within texts

No Comments

No Known Activations