INDEX

Explanations

references to specific locations or organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

olina

-0.17

ÑĪÑĤ

-0.16

elden

-0.16

ched

-0.16

 lado

-0.15

Ã©ri

-0.15

usi

-0.15

ellan

-0.14

_subs

-0.14

illa

-0.14

POSITIVE LOGITS

inf

0.16

iesz

0.15

Hab

0.15

ta

0.14

ÑĢÐ°

0.14

elves

0.14

ent

0.14

-purple

0.14

è±¡

0.14

ICES

0.14

Activations Density 0.030%

references to specific locations or organizations

No Comments

No Known Activations