INDEX

Explanations

references to specific individuals, particularly names associated with a search context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

quete

-0.15

ocratic

-0.15

Ø®Ø±

-0.15

oran

-0.15

 Kurul

-0.14

 ÏĢÎ¬

-0.14

Ð¾Ð³Ñĥ

-0.14

.wr

-0.14

ummings

-0.14

áº¡n

-0.14

POSITIVE LOGITS

nell

0.15

oline

0.14

Rud

0.14

arges

0.14

 originally

0.14

dup

0.14

 registers

0.13

ssa

0.13

.dup

0.13

 experimental

0.13

Activations Density 0.002%

references to specific individuals, particularly names associated with a search context

No Comments

No Known Activations