INDEX

Explanations

occurrences of the word "case" and its variations, indicating a focus on contextual examples or instances

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

loe

-0.16

rod

-0.16

nan

-0.15

aho

-0.15

ulp

-0.15

 bree

-0.14

thing

-0.14

issant

-0.14

coming

-0.14

self

-0.14

POSITIVE LOGITS

reeNode

0.16

ëģĶ

0.15

 Bernstein

0.14

ebnÃŃ

0.14

RYPTO

0.14

daq

0.14

 thá»©c

0.14

Ìī

0.14

LAB

0.13

 ierr

0.13

Activations Density 0.057%

occurrences of the word "case" and its variations, indicating a focus on contextual examples or instances

No Comments

No Known Activations