INDEX

Explanations

references to different levels or tiers of developers

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

urm

-0.17

 Nack

-0.14

atas

-0.14

ROAD

-0.14

ãĤ¶ãĥ¼

-0.14

lak

-0.14

sher

-0.14

istring

-0.14

uraa

-0.14

CLA

-0.13

POSITIVE LOGITS

hof

0.15

ë§ģ

0.15

haps

0.15

Ŀ

0.14

edn

0.14

ãĥªãĥ³

0.14

zeit

0.14

esses

0.14

scr

0.13

Activations Density 0.007%

references to different levels or tiers of developers

No Comments

No Known Activations