INDEX

Explanations

words or concepts related to technical and programming contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

.Sdk

-0.16

ãĤĥ

-0.16

hoff

-0.15

ragments

-0.15

åĢ

-0.14

UpInside

-0.14

fÃ¶r

-0.14

ãĥªãĥ¼ãĤº

-0.14

ijkstra

-0.14

edido

-0.14

POSITIVE LOGITS

 side

0.18

 Side

0.16

-side

0.16

urette

0.16

Side

0.16

SIDE

0.15

side

0.14

Ð°Ð»Ñĥ

0.14

ALE

0.14

_side

0.14

Activations Density 0.025%

words or concepts related to technical and programming contexts

No Comments

No Known Activations