INDEX

Explanations

punctuation marks, particularly commas

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

ergy

-0.16

çĴ

-0.15

.documentation

-0.15

renc

-0.15

hread

-0.14

antan

-0.14

ãĥ§

-0.14

 Teknik

-0.14

oshi

-0.14

ectar

-0.14

POSITIVE LOGITS

à¸´à¸Ķ

0.17

usat

0.16

ê°ĳ

0.15

Haz

0.15

Haz

0.14

uf

0.14

uber

0.14

å£

0.14

 saying

0.14

Activations Density 0.036%

punctuation marks, particularly commas

No Comments

No Known Activations