INDEX

Explanations

terms related to mechanical components and their functionalities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

lse

-0.15

cott

-0.15

gate

-0.15

riv

-0.14

imens

-0.14

Activ

-0.14

ssel

-0.14

 memoria

-0.14

 xáº¿p

-0.13

 Ð¾ÑĤÐ²

-0.13

POSITIVE LOGITS

nut

0.15

urning

0.15

nut

0.14

ãĥ³ãĥĢ

0.14

zw

0.14

cob

0.14

Nut

0.13

isay

0.13

ACHI

0.13

 Quarter

0.13

Activations Density 0.065%

terms related to mechanical components and their functionalities

No Comments

No Known Activations