INDEX

Explanations

references to geographical locations and related entities in a structured context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

imoto

-0.14

sher

-0.14

.Accessible

-0.14

æ¡£

-0.14

/*č↵

-0.13

cratch

-0.13

TTY

-0.13

Reporter

-0.13

POSITIVE LOGITS

edom

0.14

Ð¾ÑģÑĤÐ°Ð²

0.14

hus

0.14

azio

0.14

gom

0.14

cre

0.14

letics

0.13

trap

0.13

ihu

0.13

ihan

0.13

Activations Density 0.009%

references to geographical locations and related entities in a structured context

No Comments

No Known Activations