INDEX

Explanations

dialogue or speech attribution in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

 Carrier

-0.15

ASSERT

-0.14

Ou

-0.14

Ì§

-0.14

 carrier

-0.14

leurs

-0.13

oup

-0.13

Ø§ÙĨØ§Øª

-0.13

rtc

-0.13

POSITIVE LOGITS

azzi

0.18

redi

0.16

 lunch

0.15

ÑĢÐ°Ð±

0.14

beg

0.14

ACHI

0.14

achi

0.14

beg

0.14

ermo

0.14

LAR

0.13

Activations Density 0.062%

dialogue or speech attribution in the text

No Comments

No Known Activations