INDEX

Explanations

references to reversals or transformations, particularly in mathematical or conceptual contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

inou

-0.15

 cardi

-0.15

 Binder

-0.14

ized

-0.14

ÙĪØ±Ø§ÙĨ

-0.14

rieve

-0.14

ÑģÑĤÑĢÐ¸

-0.14

 Curt

-0.14

nap

-0.14

POSITIVE LOGITS

Ú¯Ø§ÙĨÛĮ

0.14

hci

0.14

ohn

0.14

 Tubes

0.14

ucha

0.14

igans

0.14

ÑĨÑĸ

0.13

seau

0.13

andan

0.13

Rule

0.13

Activations Density 0.024%

references to reversals or transformations, particularly in mathematical or conceptual contexts

No Comments

No Known Activations