INDEX

Explanations

numeric or code-like representations, likely related to structured data or formatting

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

imony

-0.17

jni

-0.15

rive

-0.15

lasses

-0.15

plen

-0.15

asar

-0.15

cxx

-0.15

ipment

-0.14

ledged

-0.14

arend

-0.14

POSITIVE LOGITS

elt

0.16

ouri

0.14

umb

0.14

ocker

0.14

ÑĢÐ¾Ð´

0.13

ux

0.13

overs

0.13

ãĥ¼ãĥĨãĤ£

0.13

Bu

0.13

 Sharp

0.13

Activations Density 0.024%

numeric or code-like representations, likely related to structured data or formatting

No Comments

No Known Activations