INDEX

Explanations

terms related to attaching or connection

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

jte

-0.15

jni

-0.14

conde

-0.14

ingen

-0.14

naire

-0.14

erer

-0.14

Ø§ÙĨØ³

-0.14

à¹īà¸ĩ

-0.13

Î½Î·ÏĤ

-0.13

ing

-0.13

POSITIVE LOGITS

endum

0.18

/embed

0.17

iline

0.16

oll

0.16

ħ§

0.15

itude

0.15

sel

0.15

æ³Ĭ

0.14

.radians

0.14

ADDE

0.14

Activations Density 0.036%

terms related to attaching or connection

No Comments

No Known Activations