INDEX

Explanations

discussions about moral ambiguity and the complexities of truth

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

itle

-0.16

reet

-0.15

WXYZ

-0.15

-0.14

_RESOLUTION

-0.14

ophon

-0.13

 ÑĢÐ°Ð²Ð½Ð¾

-0.13

 blank

-0.13

POSITIVE LOGITS

 versus

0.17

usra

0.16

 distinction

0.16

åĪ°åºķ

0.15

ãĤ¹ãĥ¬

0.15

-REAL

0.15

 whether

0.15

una

0.14

 truly

0.14

ìĿ¸ì§Ģ

0.14

Activations Density 0.152%

discussions about moral ambiguity and the complexities of truth

No Comments

No Known Activations