INDEX

Explanations

phrases related to combining multiple elements or concepts into a singular experience or summary

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

stk

-0.16

Tri

-0.14

ancode

-0.14

Tri

-0.14

Å¼e

-0.14

ÙĤØ±Ø§Ø±

-0.14

owns

-0.14

æĵ¦

-0.13

basePath

-0.13

[char

-0.13

POSITIVE LOGITS

 single

0.36

single

0.27

 SINGLE

0.27

 Single

0.25

 nutshell

0.23

Single

0.22

-single

0.22

/single

0.22

(single

0.21

 simple

0.21

Activations Density 0.148%

phrases related to combining multiple elements or concepts into a singular experience or summary

No Comments

No Known Activations